CN105447274A - Method of performing coastal wetland drawing for medium-resolution remote sensing image by utilizing object-oriented classification technology - Google Patents
Method of performing coastal wetland drawing for medium-resolution remote sensing image by utilizing object-oriented classification technology Download PDFInfo
- Publication number
- CN105447274A CN105447274A CN201510975435.2A CN201510975435A CN105447274A CN 105447274 A CN105447274 A CN 105447274A CN 201510975435 A CN201510975435 A CN 201510975435A CN 105447274 A CN105447274 A CN 105447274A
- Authority
- CN
- China
- Prior art keywords
- classification
- seashore wetland
- remote sensing
- feature
- wetland
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 241001149258 Sporobolus alterniflorus Species 0.000 claims description 33
- 238000012258 culturing Methods 0.000 claims description 31
- 239000013535 sea water Substances 0.000 claims description 29
- 240000002044 Rhizophora apiculata Species 0.000 claims description 25
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 23
- 238000001228 spectrum Methods 0.000 claims description 16
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 5
- 239000002689 soil Substances 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 241000282693 Cercopithecidae Species 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 abstract description 6
- 150000003839 salts Chemical class 0.000 abstract description 5
- 230000011218 segmentation Effects 0.000 abstract description 2
- 238000002203 pretreatment Methods 0.000 abstract 2
- 238000012360 testing method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000004069 differentiation Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method of performing coastal wetland drawing for a medium-resolution remote sensing image by utilizing an object-oriented classification technology and relates to the method of performing coastal wetland drawing for the medium-resolution remote sensing image. The provided method is mainly to solve the problems that the various types of the wetlands cannot be distinguished exactly by a traditional remote sensing image classification method, the classified results generally have a spiced salt phenomenon and an enclave phenomenon, and the traditional remote sensing image classification method is not applicable for the coastal wetland drawing of the medium-resolution remote sensing image. The method of performing coastal wetland drawing for the medium-resolution remote sensing image by utilizing the object-oriented classification technology comprises the steps of performing pre-treatment for an Landsat8 OLI image and DEM data; performing multi-resolution segmentation for the Landsat8 OLT image after subjected to pre-treatment in the step 1; exporting to generate a coastal wetland typical ground object spectral curve; determining typical ground object characteristics which can be used for distinguishing the coastal wetlands; obtaining a preliminary classification result; optimizing the classification result; and exporting the classification result, that is, the coastal wetland typical ground object, and generating each coastal wetland type vector. The method of performing coastal wetland drawing for the medium-resolution remote sensing image by utilizing the object-oriented classification technology is used in the field of coastal wetland drawing.
Description
Technical field
The present invention relates to the method for intermediate resolution remote sensing images being carried out to seashore wetland drawing.
Background technology
Seashore wetland is positioned at the staggered transitional zone of land and marine ecosystems, have both the ecotype of sea, Lu Tezheng, have the special hydrology, vegetation, soil characteristic, in maintenance bio-diversity, the aspects such as carbon stores, regulate the climate, Control pollution play an important role.In recent years, along with the continuous impact of climate change and mankind's activity, coastal region physical environment and ecoscape are changed significantly.Therefore, obtain seashore wetland landscape pattern information quickly and accurately, for the management of wetland resource, the Significance of Sustainable Development of coastland exploitation and resource is great.But seashore wetland is located in extra large land ecotone, and the vegetation such as mangrove, Spartina alterniflora is distributed in the open smooth shoal, mesolittoral zone of physical features, and make on-site inspection be difficult to carry out, conventional means is accurately located and investigated time and effort consuming, and poor in timeliness.Remote sensing technology can be carried out on a large scale, nearly earth observation in real time.Therefore remote sensing technology is utilized to monitor seashore wetland type of ground objects, not only cost-saving, also can chart fast and accurately.
OO remote Sensing Interpretation method is, by Image Segmentation, homogeneity pixel is merged into object, then distinguishes atural object class method for distinguishing according to differences such as spectrum, shape, texture, topologys between object.It breaches the limitation that conventional sorting methods carries out based on pixel classifying and processing, overcome the shortcoming that classification results exists spiced salt phenomenon, and with the object containing more multi-semantic meaning information for processing unit, data operation quantity can be reduced and improve classification effectiveness, the remote sensing image classification of higher level can be realized again.The method is the sensor information extracting method based on cognitive model, more presses close to the cognitive process of the mankind, has become sensor information and has extracted one of main research direction in field.
Due to the periodic motion of wave and tide, the impact of mankind's activity in addition, make coastland view be tending towards complicated, traditional seashore wetland sorting technique, only utilizes spectral signature, can not accurately distinguish wetland classification.
Summary of the invention
The present invention will solve traditional Classifying Method in Remote Sensing Image accurately cannot distinguish various wetland classification, and after classification there is " spiced salt phenomenon ", " enclave phenomenon " in result usually, be not suitable for the seashore wetland drawing of intermediate-resolution remote sensing image, and provide a kind of object oriented classification technology that utilizes the method for seashore wetland drawing is carried out to intermediate resolution remote sensing images.
Utilize object oriented classification technology to carry out a method for seashore wetland drawing to intermediate resolution remote sensing images, it is characterized in that realizing according to the following steps:
Step one: download Landsat8OLI image and digital elevation model and dem data, and respectively pre-service is carried out to Landsat8OLI image and dem data, anticipation is carried out to pretreated Landsat8OLI image, determine seashore wetland typical feature, comprising: mangrove, Spartina alterniflora, seawater, beach, culturing pool and building site;
Wherein, described orthorectify and geometric exact correction are comprised to Landsat8OLI Yunnan snub-nosed monkey;
Described projection transform is comprised to dem data pre-service, make dem data and Landsat8OLI image coordinate systems compliant, and in ArcGIS, utilize Fill instrument to carry out filling out hollow peak clipping process;
Step 2: carry out multi-scale division to Landsat8OLI image pretreated in step one, merges into object according to homogeney standard by adjacent picture elements, obtains imaged object layer;
Step 3: based on eCognitionDeveloper8.64 software, according to on-site inspection sampling point, obtain seashore wetland typical feature sample object, utilize LayerValues instrument in Objectfeatures to calculate the spectrum average of seashore wetland typical feature sample object at each wave band of Landsat8OLI image, and derive the generation seashore wetland typical feature curve of spectrum;
Step 4: according to the seashore wetland typical feature curve of spectrum obtained in step 3, combined imaging feature, determines to can be used for distinguish seashore wetland typical feature feature, and based on the calculating of each feature of eCognitionDeveloper8.64 software simulating;
Step 5: the seashore wetland typical feature feature utilizing step 4 to obtain, by setting threshold value and sequence of extraction, delimit seashore wetland in-scope, extracts each seashore wetland typical feature object successively, obtain preliminary classification result;
Step 6: treatment of details is carried out to step 5 gained preliminary classification result, in conjunction with shape, topology, the mixed point patch of atural object spatial relationship feature merger, Optimum Classification result;
Step 7: derive classification results and seashore wetland typical feature object, generate each seashore wetland type vector;
Step 8: make seashore wetland type map in ArcGIS software.
Invention effect:
The present invention is directed to traditional Classifying Method in Remote Sensing Image and accurately cannot distinguish various wetland classification, and after classification there is " spiced salt phenomenon ", " enclave phenomenon " in result usually, be not suitable for the seashore wetland drawing of intermediate-resolution remote sensing image, propose based on Object-oriented Technique, utilize the features such as the spectrum of object, shape, topology and atural object spatial relationship, be aided with digital elevation model (DEM), pass through band combination, setting threshold value successively extracts seashore wetland typical feature object, makes seashore wetland Map of Distributions of Types.
Landsat8 is the road resource satellite that NASA (NASA) launched in 2013, its OLI land imager (OperationalLandImager) of carrying has 9 wave bands, the present invention uses 6 multi light spectrum hands (B:0.45 ~ 0.51 μm, G:0.53 ~ 0.59 μm, R:0.64 ~ 0.67 μm, NIR:0.85 ~ 0.88 μm, SWIR1:1.57 ~ 1.65 μm, SWIR2:2.11 ~ 2.29 μm), spatial resolution 30 meters, revisiting period 16 days, compare other Landsat series of satellites, its radiometric resolution brings up to 16bit, make terrestrial object information meticulousr, more be conducive to ground object information extraction.Landsat series of satellites has been proved and has been applicable to coastland Wetland Type information extraction.
Due to the periodic motion of wave and tide, the impact of mankind's activity in addition, make coastland view be tending towards complicated, traditional seashore wetland sorting technique, only utilizes spectral signature, can not accurately distinguish wetland classification.The present invention is directed to traditional Classifying Method in Remote Sensing Image and clearly cannot distinguish various wetland classification, and after classification there is " spiced salt phenomenon ", " enclave phenomenon " in result usually, be not suitable for the seashore wetland drawing of intermediate-resolution remote sensing image, propose based on Object-oriented Technique, utilize the features such as the spectrum of object, texture, shape, topology and atural object spatial relationship, be aided with DEM, pass through band combination, setting threshold value successively extracts wetland object, makes seashore wetland Map of Distributions of Types.
The present invention relates to the Classifying Method in Remote Sensing Image of Object-oriented Technique, the information such as shape, texture, topology and atural object spatial relationship are added in assorting process, and be aided with DEM, extract the seashore wetland type area space distribution information in intermediate resolution remote sensing image (Landsat8OLI) fast and accurately, thus make seashore wetland type map.
Accompanying drawing explanation
Fig. 1 is seashore wetland typical feature spectral curve;
Fig. 2 is seashore wetland classifying rules collection figure;
Fig. 3 is test site remote sensing image; Wherein, test site remote sensing image (R:G:B=SWIR1:NIR:R);
Fig. 4 is test site seashore wetland classification results figure.
Embodiment
Technical solution of the present invention is not limited to following cited embodiment, also comprises the combination in any between each embodiment.
Embodiment one: a kind of object oriented classification technology that utilizes of present embodiment realizes according to the following steps to the method that intermediate resolution remote sensing images carry out seashore wetland drawing:
Step one: download Landsat8OLI image and digital elevation model and dem data, and carry out pre-service respectively, anticipation is carried out to pretreated Landsat8OLI image, determines seashore wetland typical feature;
Wherein, described Landsat8OLI Yunnan snub-nosed monkey comprises orthorectify and geometric exact correction; DEM pre-service comprises projection transform, makes DEM and Landsat8OLI image coordinate systems compliant, and in ArcGIS, utilize Fill instrument to carry out filling out hollow peak clipping process.
Step 2: carry out multi-scale division to Landsat8OLI image pretreated in step one, merges into object according to homogeney standard by adjacent picture elements, obtains imaged object layer;
Step 3: based on eCognitionDeveloper8.64 software, according to on-site inspection sampling point, obtain seashore wetland typical feature sample object, utilize LayerValues instrument in Objectfeatures to calculate the spectrum average of seashore wetland typical feature sample object at each wave band of Landsat8OLI image, and derive the generation seashore wetland typical feature curve of spectrum;
Step 4: according to the seashore wetland typical feature curve of spectrum obtained in step 3, combined imaging feature, determines the feature that can be used for distinguishing seashore wetland typical feature;
Step 5: the seashore wetland typical feature feature obtained according to step 4, by setting threshold value and sequence of extraction, delimit seashore wetland in-scope, extracts each seashore wetland typical feature object successively, obtain preliminary classification result.
Step 6: treatment of details is carried out to step 5 gained preliminary classification result, in conjunction with shape, topology, the mixed point patch of atural object spatial relationship feature merger, Optimum Classification result;
Step 7: derive classification results and seashore wetland typical feature object, generate each seashore wetland type vector;
Step 8: make seashore wetland type map in ArcGIS software.
Landsat8OLI image in step one, orbit number is P124R45, and on January 1 2015 time, dem data is SRTM data, and ranks number are P58R08.The seashore wetland typical feature determined comprises: mangrove, Spartina alterniflora, seawater, beach, culturing pool and building site.
Embodiment two: present embodiment and embodiment one unlike: determine in step 4 that the feature that can be used for distinguishing seashore wetland typical feature calculates based on eCognitionDeveloper8.64 software: according to normalized differential vegetation index (NDVI), surface humidity index (LSWI), soil lightness index (SBI), normalization water body index (NDWI) formula, utilize the above-mentioned feature that counts of the calculating object respectively of CreateArithmeticFeature instrument in Objectfeatures; Tone (Hue) feature after band combination is obtained by HIS conversion; And using DEM pretreated in step one as characteristic layer, utilize LayerValues instrument to calculate the DEM feature of imaged object.
Other step and parameter identical with embodiment one.
Embodiment three: present embodiment and embodiment one or two unlike: described step 5 is specially:
(1), in step 2 gained imaged object layer, utilize the result of calculation of step 4, DEM is less than or equal to 10 and the object of NDWI between-0.08 and 0.32 is seashore wetland in-scope, called after " coastal area ";
(2), in coastal area, meet Hue (R='NIR', G='SWIR1', B='SWIR2') feature is between 0.7 and 1 and the object that NDVI is less than 0.15 is water body and beach, and the object naming do not satisfied condition is " residue coastal area 1 ";
(3), in water body and beach, meet LSWI between 0.12 and 0.31 and the object that NDVI is greater than 0 is beach, the object naming do not satisfied condition is " residue water body 1 ";
(4), remain in water body 1, meet NDWI between 0.06 and 0.32 and the object that DEM is less than or equal to 1 is seawater, and seawater object is merged, make adjacent seawater object merging be large patch, the object naming do not satisfied condition is " residue water body 2 ";
(5), in residue water body 2, meet and to adjoin with seawater or beach and the object that DEM is less than or equal to 1 is beach; In this part beach and 3, beach sum is beach classification results;
(6), remain in water body 2, not meeting the object extracting beach condition in 5 is culturing pool;
(7), remain in coastal area 1, meet Hue (R='SWIR1', G='NIR', B='SWIR2') feature is between 0.28 and 0.35 and the object that LSWI is more than or equal to 0.13 is mangrove, and the object naming do not satisfied condition is " residue coastal area 2 ";
(8), remain in coastal area 2, meeting the object of SBI between 17710 and 30000 is building site, and after repeatedly classifying, remaining object comparatively pure is Spartina alterniflora.
Other step and parameter identical with embodiment one or two.
Embodiment four: one of present embodiment and embodiment one to three unlike: described step 6 is specially:
(1) carry out merging in class to mangrove, Spartina alterniflora's classification;
(2) utilize girth area ratio to adjoin in the maximum classification of ratio shared by being divided in the object merging of Spartina alterniflora or mangrove to its contiguous object by mistake;
(3) utilize area, DEM feature to be divided into the object merging of Spartina alterniflora in culturing pool classification stalk position in the pool in culturing pool object by mistake;
(4) improve seawater nicety of grading, low altitude area is mixed and is divided into the culturing pool object extraction of seawater to go out;
(5) the little broken patch formed in assorting process is integrated.
Other step and parameter identical with one of embodiment one to three.
Embodiment five: one of present embodiment and embodiment one to four unlike: described step 6 is specially:
Described (1) carries out merging in class being specially to mangrove, Spartina alterniflora's classification:
Mergeregion (mangrove);
Mergeregion (Spartina alterniflora);
Described (2) utilize girth area ratio to be specially being divided into shared adjoining in the maximum classification of ratio in the object merging of Spartina alterniflora or mangrove to its contiguous object by mistake:
Removeobjects (' mangrove ', ' Spartina alterniflora '; With0.62<=P A<=0.76);
Described (3) utilize area, DEM feature to be divided into the object merging of Spartina alterniflora to be specially in culturing pool classification stalk position in the pool in culturing pool object by mistake:
Removeobjects (' Spartina alterniflora '; WithDEM<=1andArea<=250pixel, into' culturing pool ');
Described (4) improve seawater nicety of grading, are mixed low altitude area and are divided into the culturing pool object extraction of seawater to go out:
Removeobjects (' seawater '; WithArea<=500pixel, into ' culturing pool ');
Described (5) integrate the little broken patch formed in assorting process:
Removeobjects('none'；withArea<＝10pixel)。
Other step and parameter identical with one of embodiment one to four.
Emulation experiment:
Step one: download test Landsat8OLI image used, orbit number is P124R45, January 1 2015 time, download SRTM90 Miho Dockyard EM data, ranks number are P58R08.For eliminating landform distortion, the dem data of test site is utilized to carry out orthorectify to OLI image; For eliminating geometric distortion, utilizing 1:50000 terrain data, in ERDAS software, choosing ground control point, geometric exact correction is carried out to the image after orthorectify.In ArcGIS software, projection transform is carried out to DEM, make DEM and Landsat8OLI image coordinate systems compliant, and in ARCGIS, utilize Fill instrument to fill out hollow peak clipping process to DEM, remove pseudo-landform.Anticipation is carried out to Landsat8OLI image, determines seashore wetland typical feature type, comprise mangrove, Spartina alterniflora, seawater, beach, culturing pool, building site.
Step 2: carry out multi-scale division to Landsat8OLI image pretreated in step one, merges into object according to homogeney standard by adjacent picture elements, obtains imaged object layer.Table 1 is presented at the optimum configurations of multi-scale division in object oriented classification process, as the homogeneous standard of judgement pixel.
Table 1. multi-scale division optimum configurations
| Segmentation yardstick | Color factor | Form factor | Smoothness | Degree of compacting |
| 60 | 0.8 | 0.2 | 0.5 | 0.5 |
Step 3: according to on-site inspection sampling point, obtain test site seashore wetland typical feature sample object, this example calculates the spectrum characteristic parameter of each seashore wetland typical feature sample object in eCognitionDeveloper8.64 software, and derives the generation typical feature curve of spectrum, as Fig. 1;
Step 4: utilize the seashore wetland typical feature curve of spectrum obtained in step 3, and combined imaging feature, determine the feature that can be used for distinguishing seashore wetland typical feature, based on eCognitionDeveloper8.64 software, according to normalized differential vegetation index (NDVI), surface humidity index (LSWI), soil lightness index (SBI), the formula such as normalization water body index (NDWI), utilize the above-mentioned feature that counts of the calculating object respectively of CreateArithmeticFeature instrument in Objectfeatures, tone (Hue) feature after band combination is obtained by HIS conversion, and using pretreated DEM as characteristic layer, layervalues instrument is utilized to calculate the DEM feature of imaged object,
Step 5: first utilize DEM feature determination elevation to be less than or equal to 10 meters, and the scope of NDWI index between-0.08 and 0.32 is coastal area, then, the all characteristic informations utilizing step 4 to obtain, determine the feature of differentiation seashore wetland classification, threshold value and order, be separated of all categories from coastal area successively, due to complicacy and the crumbliness of coastal atural object, single rule is difficult to extract completely, the present invention utilizes the mode of Feature Combination to distinguish atural object further, concrete classifying rules is in table 2, and Fig. 2, in table 2, sequence of extraction is consistent with sequence of extraction in Fig. 2.(8. the left branch bottom first carries out, then carries out 9., and 5. the right branch bottom first carries out, carry out 6. again, and other types perform from top to bottom)
Table 2 seashore wetland classifying rules collection
*: base area object space relation: first, seawater object is carried out union operation, namely exposed waters will merge into a large objects, then, by adjacent seawater in residue water body 2 or beach and the chip residue water body 2 be positioned within DEM<=1 is categorized as beach, other residue water bodys 2 are divided into culturing pool.*: the residue coastal area 2 after separating for several times is comparatively pure, is divided into Spartina alterniflora, but still have the cultivating pool ridge or lack of water culturing pool is obscured with it, can according to the special shape facility in the ridge, the pool and atural object spatial relationship, and minimizing is obscured.
Step 6: carry out treatment of details to step 5 gained PRELIMINARY RESULTS, in this example, pending details is as follows:
The culturing pool of soil information at the bottom of reflection tank between the cultivating pool ridge of 1, normal growth vegetation or because of lack of water, its spectral information is subject to the interference of surrounding water spectral information, causes it to be easily mixedly divided into mangrove or Spartina alterniflora;
2, in low altitude area, there is the phenomenon of to be enclosed and cultivated by the atural objects such as beach, Spartina alterniflora, mangrove as culturing pool, similar to seawater on image feature and locus for this culturing pool, cause it to be easily mixedly divided into seawater;
3, in assorting process, easily form little broken patch, need integrate.
Mix sub-category in conjunction with feature differentiation such as shape, topology, atural object spatial relationships, and the little broken patch of merger, Optimum Classification result.
As follows to above-mentioned treatment of details process:
1, carry out merging in class to mangrove, Spartina alterniflora's classification, after merging, true mangrove, Spartina alterniflora are in larger patch, then consider that the ridge, the pool and culturing pool object present the polygon and unique shape feature that area is little, utilize girth area ratio (P A) this type of to be obscured in the classification that in object merging to its contiguous object, shared adjacent ratio is maximum.
Mergeregion (mangrove)
Mergeregion (Spartina alterniflora)
Removeobjects (' mangrove ', ' Spartina alterniflora '; With0.62<=P A<=0.76)
Removeobjects (' Spartina alterniflora '; WithDEM<=1andArea<=250pixel, into' culturing pool ')
2, the culturing pool of low altitude area, is not communicated with open seawater usually, and comparatively broken patch is less, utilizes this character to can further improve the nicety of grading of seawater.
Removeobjects (' seawater '; WithArea<=500pixel, into ' culturing pool ')
3、Removeobjects('none'；withArea<＝10pixel)
Due to the complicacy on earth's surface and the nonuniqueness of image feature, service regeulations algorithm is difficult to atural object to distinguish completely, but overall classification accuracy of the present invention reaches more than 91%, and classifying quality is better, if raising nicety of grading, suitably carry out trickle amendment in conjunction with visual interpretation.
Step 7: derive Wetland classification, generate each seashore wetland type vector;
Step 8: make seashore wetland type map in ArcGIS software.
Technical solution of the present invention is not limited to above cited concrete remotely-sensed data, also comprises the object-oriented classification method of various remote sensing image.
Claims (5)
1. utilize object oriented classification technology to carry out a method for seashore wetland drawing to intermediate resolution remote sensing images, it is characterized in that realizing according to the following steps:
Step one: download Landsat8OLI image and digital elevation model and dem data, and respectively pre-service is carried out to Landsat8OLI image and dem data, anticipation is carried out to pretreated Landsat8OLI image, determine seashore wetland typical feature, comprising: mangrove, Spartina alterniflora, seawater, beach, culturing pool and building site;
Wherein, described orthorectify and geometric exact correction are comprised to Landsat8OLI Yunnan snub-nosed monkey;
Described projection transform is comprised to dem data pre-service, make dem data and Landsat8OLI image coordinate systems compliant, and in ArcGIS, utilize Fill instrument to carry out filling out hollow peak clipping process;
Step 2: carry out multi-scale division to Landsat8OLI image pretreated in step one, merges into object according to homogeney standard by adjacent picture elements, obtains imaged object layer;
Step 3: based on eCognitionDeveloper8.64 software, according to on-site inspection sampling point, obtain seashore wetland typical feature sample object, utilize LayerValues instrument in Objectfeatures to calculate the spectrum average of seashore wetland typical feature sample object at each wave band of Landsat8OLI image, and derive the generation seashore wetland typical feature curve of spectrum;
Step 4: according to the seashore wetland typical feature curve of spectrum obtained in step 3, combined imaging feature, determines to can be used for distinguish seashore wetland typical feature feature, and based on the calculating of each feature of eCognitionDeveloper8.64 software simulating;
Step 5: the seashore wetland typical feature feature utilizing step 4 to obtain, by setting threshold value and sequence of extraction, delimit seashore wetland in-scope, extracts each seashore wetland typical feature object successively, obtain preliminary classification result;
Step 6: treatment of details is carried out to step 5 gained preliminary classification result, in conjunction with shape, topology, the mixed point patch of atural object spatial relationship feature merger, Optimum Classification result;
Step 7: derive classification results and seashore wetland typical feature object, generate each seashore wetland type vector;
Step 8: make seashore wetland type map in ArcGIS software.
2. a kind of object oriented classification technology that utilizes according to claim 1 carries out the method for seashore wetland drawing to intermediate resolution remote sensing images, it is characterized in that described step 4 is specially:
CreateArithmeticFeature instrument in Objectfeatures is utilized according to formulae discovery normalized differential vegetation index, surface humidity index, soil lightness index, normalization water body index, to obtain the tone characteristics after band combination by HIS conversion; And using DEM pretreated in step one as characteristic layer, utilize LayerValues instrument to calculate the DEM feature of imaged object.
3. a kind of object oriented classification technology that utilizes according to claim 1 and 2 carries out the method for seashore wetland drawing to intermediate resolution remote sensing images, it is characterized in that described step 5 is specially:
(1), in step 2 gained imaged object layer, utilize the result of calculation of step 4, DEM is less than or equal to 10 and the object of NDWI between-0.08 and 0.32 is seashore wetland in-scope, called after " coastal area ";
(2), in coastal area, meet tone characteristics (R='NIR', G='SWIR1', B='SWIR2') between 0.7 and 1 and the object that NDVI is less than 0.15 is water body and beach, the object naming do not satisfied condition is " residue coastal area 1 ";
(3), in water body and beach, meet LSWI between 0.12 and 0.31 and the object that NDVI is greater than 0 is beach, the object naming do not satisfied condition is " residue water body 1 ";
(4), remain in water body 1, meet NDWI between 0.06 and 0.32 and the object that DEM is less than or equal to 1 is seawater, and seawater object is merged, make adjacent seawater object merging be large patch, the object naming do not satisfied condition is " residue water body 2 ";
(5), in residue water body 2, meet and to adjoin with seawater or beach and the object that DEM is less than or equal to 1 is beach; In this part beach and 3, beach sum is beach classification results;
(6), remain in water body 2, not meeting the object extracting beach condition in 5 is culturing pool;
(7), remain in coastal area 1, meet tone characteristics (R='SWIR1', G='NIR', B='SWIR2') between 0.28 and 0.35 and the object that LSWI is more than or equal to 0.13 is mangrove, the object naming do not satisfied condition is " residue coastal area 2 ";
(8), remain in coastal area 2, meeting the object of SBI between 17710 and 30000 is building site, and after repeatedly classifying, remaining object comparatively pure is Spartina alterniflora.
4. a kind of object oriented classification technology that utilizes according to claim 3 carries out the method for seashore wetland drawing to intermediate resolution remote sensing images, it is characterized in that described step 6 is specially:
(1) carry out merging in class to mangrove, Spartina alterniflora's classification;
(2) utilize girth area ratio to adjoin in the maximum classification of ratio shared by being divided in the object merging of Spartina alterniflora or mangrove to its contiguous object by mistake;
(3) utilize area, DEM feature to be divided into the object merging of Spartina alterniflora in culturing pool classification stalk position in the pool in culturing pool object by mistake;
(4) improve seawater nicety of grading, low altitude area is mixed and is divided into the culturing pool object extraction of seawater to go out;
(5) the little broken patch formed in assorting process is integrated.
5. a kind of object oriented classification technology that utilizes according to claim 4 carries out the method for seashore wetland drawing to intermediate resolution remote sensing images, it is characterized in that
Described (1) carries out merging in class being specially to mangrove, Spartina alterniflora's classification:
Mergeregion (mangrove);
Mergeregion (Spartina alterniflora);
Described (2) utilize girth area ratio to be specially being divided into shared adjoining in the maximum classification of ratio in the object merging of Spartina alterniflora or mangrove to its contiguous object by mistake:
Removeobjects (' mangrove ', ' Spartina alterniflora '; With0.62<=P A<=0.76);
Described (3) utilize area, DEM feature to be divided into the object merging of Spartina alterniflora to be specially in culturing pool classification stalk position in the pool in culturing pool object by mistake:
Removeobjects (' Spartina alterniflora '; WithDEM<=1andArea<=250pixel, into' culturing pool ');
Described (4) improve seawater nicety of grading, are mixed low altitude area and are divided into the culturing pool object extraction of seawater to go out:
Removeobjects (' seawater '; WithArea<=500pixel, into ' culturing pool ');
Described (5) integrate the little broken patch formed in assorting process:
Removeobjects('none'；withArea<＝10pixel)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510975435.2A CN105447274B (en) | 2015-12-22 | 2015-12-22 | A method of seashore wetland drawing being carried out to intermediate resolution remote sensing images using object oriented classification technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510975435.2A CN105447274B (en) | 2015-12-22 | 2015-12-22 | A method of seashore wetland drawing being carried out to intermediate resolution remote sensing images using object oriented classification technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105447274A true CN105447274A (en) | 2016-03-30 |
| CN105447274B CN105447274B (en) | 2018-07-27 |
Family
ID=55557445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510975435.2A Expired - Fee Related CN105447274B (en) | 2015-12-22 | 2015-12-22 | A method of seashore wetland drawing being carried out to intermediate resolution remote sensing images using object oriented classification technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105447274B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709517A (en) * | 2016-12-19 | 2017-05-24 | 航天恒星科技有限公司 | Mangrove recognition method and system |
| CN108256534A (en) * | 2018-01-29 | 2018-07-06 | 中国科学院地理科学与资源研究所 | A kind of raft formula marine cultivation region extracting method based on high score remote sensing image |
| CN108388828A (en) * | 2017-07-13 | 2018-08-10 | 中国科学院遥感与数字地球研究所 | A kind of seashore wetland land cover pattern information extracting method of comprehensive multi- source Remote Sensing Data data |
| CN109657598A (en) * | 2018-12-13 | 2019-04-19 | 宁波大学 | Seashore wetland Classification in Remote Sensing Image method based on Stratified Strategy |
| CN109726705A (en) * | 2019-01-24 | 2019-05-07 | 中国科学院地理科学与资源研究所 | Extracting method, device and the electronic equipment of mangrove information |
| CN109753916A (en) * | 2018-12-28 | 2019-05-14 | 厦门理工学院 | A kind of vegetation index spatial scaling model building method and device |
| CN110096997A (en) * | 2019-04-29 | 2019-08-06 | 宁波大学 | A kind of littoral zone sophisticated category method of integrated multi- source Remote Sensing Data data |
| CN110296690A (en) * | 2019-06-06 | 2019-10-01 | 中国科学院东北地理与农业生态研究所 | A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103000077A (en) * | 2012-11-27 | 2013-03-27 | 中国科学院东北地理与农业生态研究所 | Method for carrying out mangrove forest map making on intermediate resolution remote sensing image by utilizing object-oriented classification method |
| CN103218806A (en) * | 2013-03-18 | 2013-07-24 | 中国科学院东北地理与农业生态研究所 | Method for detecting submerged mangrove forest distribution in high tide by facing object classification method and based on remote sensing satellite image |
| JP2014149792A (en) * | 2013-02-04 | 2014-08-21 | Sumitomo Rubber Ind Ltd | Simulation result processing method and recording medium having processing procedure thereof stored therein |
| CN104217426A (en) * | 2014-08-18 | 2014-12-17 | 中国科学院东北地理与农业生态研究所 | Object-oriented water-body extracting method based on ENVISAT ASAR and Landsat TM remote sensing data |
| CN104268559A (en) * | 2014-09-15 | 2015-01-07 | 中国科学院东北地理与农业生态研究所 | Paddy field and dry land distinguishing method based on oriented objects and medium-resolution-ration remote sensing image |
| CN104573654A (en) * | 2015-01-08 | 2015-04-29 | 中国林业科学研究院资源信息研究所 | Mangrove extraction method based on hierarchical decision tree |
-
2015
- 2015-12-22 CN CN201510975435.2A patent/CN105447274B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103000077A (en) * | 2012-11-27 | 2013-03-27 | 中国科学院东北地理与农业生态研究所 | Method for carrying out mangrove forest map making on intermediate resolution remote sensing image by utilizing object-oriented classification method |
| JP2014149792A (en) * | 2013-02-04 | 2014-08-21 | Sumitomo Rubber Ind Ltd | Simulation result processing method and recording medium having processing procedure thereof stored therein |
| CN103218806A (en) * | 2013-03-18 | 2013-07-24 | 中国科学院东北地理与农业生态研究所 | Method for detecting submerged mangrove forest distribution in high tide by facing object classification method and based on remote sensing satellite image |
| CN104217426A (en) * | 2014-08-18 | 2014-12-17 | 中国科学院东北地理与农业生态研究所 | Object-oriented water-body extracting method based on ENVISAT ASAR and Landsat TM remote sensing data |
| CN104268559A (en) * | 2014-09-15 | 2015-01-07 | 中国科学院东北地理与农业生态研究所 | Paddy field and dry land distinguishing method based on oriented objects and medium-resolution-ration remote sensing image |
| CN104573654A (en) * | 2015-01-08 | 2015-04-29 | 中国林业科学研究院资源信息研究所 | Mangrove extraction method based on hierarchical decision tree |
Non-Patent Citations (2)
| Title |
|---|
| 乐通潮: "漳江口红树林景观动态、结构特征与健康经营技术研究", 《中国博士学位论文全文数据库》 * |
| 刘伟成: "乐清湾滨海湿地不同植被带土壤养分时空分布特征", 《土壤通报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709517A (en) * | 2016-12-19 | 2017-05-24 | 航天恒星科技有限公司 | Mangrove recognition method and system |
| CN106709517B (en) * | 2016-12-19 | 2020-09-04 | 航天恒星科技有限公司 | Mangrove forest identification method and system |
| CN108388828A (en) * | 2017-07-13 | 2018-08-10 | 中国科学院遥感与数字地球研究所 | A kind of seashore wetland land cover pattern information extracting method of comprehensive multi- source Remote Sensing Data data |
| CN108256534A (en) * | 2018-01-29 | 2018-07-06 | 中国科学院地理科学与资源研究所 | A kind of raft formula marine cultivation region extracting method based on high score remote sensing image |
| CN109657598A (en) * | 2018-12-13 | 2019-04-19 | 宁波大学 | Seashore wetland Classification in Remote Sensing Image method based on Stratified Strategy |
| CN109753916A (en) * | 2018-12-28 | 2019-05-14 | 厦门理工学院 | A kind of vegetation index spatial scaling model building method and device |
| CN109726705A (en) * | 2019-01-24 | 2019-05-07 | 中国科学院地理科学与资源研究所 | Extracting method, device and the electronic equipment of mangrove information |
| CN109726705B (en) * | 2019-01-24 | 2020-07-31 | 中国科学院地理科学与资源研究所 | Mangrove forest information extraction method and device and electronic equipment |
| CN110096997A (en) * | 2019-04-29 | 2019-08-06 | 宁波大学 | A kind of littoral zone sophisticated category method of integrated multi- source Remote Sensing Data data |
| CN110296690A (en) * | 2019-06-06 | 2019-10-01 | 中国科学院东北地理与农业生态研究所 | A kind of Tideland resources rapid remote sensing extracting method based on Google Earth Engine Cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105447274B (en) | 2018-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mao et al. | National wetland mapping in China: A new product resulting from object-based and hierarchical classification of Landsat 8 OLI images | |
| CN105447274A (en) | Method of performing coastal wetland drawing for medium-resolution remote sensing image by utilizing object-oriented classification technology | |
| CN109919875B (en) | High-time-frequency remote sensing image feature-assisted residential area extraction and classification method | |
| CN111598045B (en) | Remote sensing farmland change detection method based on object spectrum and mixed spectrum | |
| CN101840581B (en) | Method for extracting profile of building from satellite remote sensing image | |
| Dinuls et al. | Tree species identification in mixed Baltic forest using LiDAR and multispectral data | |
| CN107392130A (en) | Classification of Multispectral Images method based on threshold adaptive and convolutional neural networks | |
| CN104361338A (en) | Peat bog information extracting method based on ENVISAT ASAR, Landsat TM and DEM data | |
| CN109977991A (en) | Forest resourceies acquisition method based on high definition satellite remote sensing | |
| CN116012723A (en) | Wetland type extraction method and device based on time sequence remote sensing image and electronic equipment | |
| CN109584284A (en) | A kind of seashore wetland ground object sample extracting method of hierarchical decision making | |
| Feng et al. | A hierarchical extraction method of impervious surface based on NDVI thresholding integrated with multispectral and high-resolution remote sensing imageries | |
| CN107688776A (en) | A kind of urban water-body extracting method | |
| CN115880487A (en) | Forest laser point cloud branch and leaf separation method based on deep learning method | |
| Liu et al. | Land use and land cover mapping in China using multimodal fine-grained dual network | |
| Guo et al. | Mozambique flood (2019) caused by tropical cyclone idai monitored from sentinel-1 and sentinel-2 images | |
| Chen et al. | 3D model construction and ecological environment investigation on a regional scale using UAV remote sensing | |
| Nyamekye et al. | Examining the performances of true color RGB bands from Landsat-8, Sentinel-2 and UAV as stand-alone data for mapping artisanal and Small-Scale Mining (ASM) | |
| Ma et al. | Feature-enhanced deep learning network for digital elevation model super-resolution | |
| Wang et al. | Extraction of palaeochannel information from remote sensing imagery in the east of Chaohu Lake, China | |
| Lu et al. | Mapping the terraces on the Loess Plateau based on a deep learning-based model at 1.89 m resolution | |
| Xu et al. | Spatiotemporal distribution of cage and raft aquaculture in China's offshore waters using object-oriented random forest classifier | |
| Liao et al. | Study on mangrove of maximum likelihood: Reclassification method in Xiezhou bay | |
| Alrassi et al. | GEOBIA For Land Use Mapping Using Worldview2 Image In Bengkak Village Coastal, Banyuwangi Regency, East Java | |
| Hao et al. | A subpixel mapping method for urban land use by reducing shadow effects |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180727 |